{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/zero-shot-transfer-learning-for-event","title":"Zero-Shot Transfer Learning for Event Extraction","arxiv_id":"1707.01066","date":"2017-07-04","proceeding":"ACL 2018 7","authors":["Lifu Huang","Heng Ji","Kyunghyun Cho","Clare R. Voss"],"abstract":"Most previous event extraction studies have relied heavily on features\nderived from annotated event mentions, thus cannot be applied to new event\ntypes without annotation effort. In this work, we take a fresh look at event\nextraction and model it as a grounding problem. We design a transferable neural\narchitecture, mapping event mentions and types jointly into a shared semantic\nspace using structural and compositional neural networks, where the type of\neach event mention can be determined by the closest of all candidate types . By\nleveraging (1)~available manual annotations for a small set of existing event\ntypes and (2)~existing event ontologies, our framework applies to new event\ntypes without requiring additional annotation. Experiments on both existing\nevent types (e.g., ACE, ERE) and new event types (e.g., FrameNet) demonstrate\nthe effectiveness of our approach. \\textit{Without any manual annotations} for\n23 new event types, our zero-shot framework achieved performance comparable to\na state-of-the-art supervised model which is trained from the annotations of\n500 event mentions.","url_abs":"http://arxiv.org/abs/1707.01066v1","url_pdf":"http://arxiv.org/pdf/1707.01066v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"zero-shot-transfer-learning-for-event","repo_url":"https://github.com/wilburOne/ZeroShotEvent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"event-extraction","task_name":"Event Extraction"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.01066","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}